Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023)

IEEE Xplore Part Number: CFP23N67-ART; ISBN: 979-8-3503-2142-5

Real Time Analysis of Blood Availability in

Accidental Cases using AI

Sanjay Singla Roop Lal Karan Singh Negi Abhinay Singh

Chandigarh University Chandigarh University Chandigarh University Chandigarh University
Punjab, India Punjab, India Punjab, India Punjab, India
[email protected] [email protected] [email protected] [email protected]
2023 5th International Conference on Inventive Research in Computing Applications (ICIRCA) | 979-8-3503-2142-5/23/$31.00 ©2023 IEEE | DOI: 10.1109/ICIRCA57980.2023.10220737

Nikhil Bisht Prince Kumar

Chandigarh University Chandigarh University
Punjab, India Punjab, India
[email protected] [email protected]

Abstract-This research study proposes a platform that can Therefore, there is a need for a platform that can quickly and
locate the nearest blood banks and hospitals in real-time to efficiently locate blood banks and hospitals to facilitate
provide quick access to medical care and blood supply in timely access to medical care and blood supply.
emergency situations. The platform utilizes Artificial
Intelligence (AI) and algorithms such as DFS, BFS, Dijkstra,
and Kruskal algorithm to determine the shortest distance to This research study proposes a platform that uses artificial
these facilities and analyze the availability of blood supply. The intelligence (AI) and algorithmic analysis to locate the
platform also enables users to find the blood bank that is best nearest blood banks and hospitals in real-time. The platform
suited for them based on factors such as distance and utilizes a range of algorithms such as DFS, BFS, Dijkstra,
availability of blood. and Kruskal algorithm to determine the shortest distance to
these facilities and analyze the availability of blood supply.
The design and implementation of the platform are discussed The proposed platform also enables users to identify the
in detail, along with test results that evaluate its effectiveness in best-suited blood bank based on factors such as distance and
real-world scenarios. With a solution that can be used to save blood availability.
lives in emergency situations, the suggested platform seeks to
significantly advance the field of healthcare technology. The
platform's use of AI and algorithms streamlines the process of By offering a solution that can save lives in emergency
locating blood banks and hospitals, allowing for more efficient situations, the platform has the potential to significantly
emergency medical care. advance the field of healthcare technology. By utilizing AI
and algorithms, the platform streamlines the process of
This research highlights the importance of technology in locating blood banks and hospitals, allowing for more
improving emergency medical services and emphasizes the efficient emergency medical care. The platform's location-
potential of AI and algorithms in providing better and more based services enable users to quickly locate the nearest
efficient healthcare services. The proposed platform is blood banks and hospitals, eliminating the need for time-
expected to assist in improving the quality of emergency consuming searches and potentially saving lives.
medical care in the future by enhancing the process of locating
blood banks and hospitals, particularly in cases of accidents.
The design and implementation of the proposed platform are
discussed in detail, along with the results of tests conducted
Keywords: Algorithms, Blood banks, Hospitals, Real- to evaluate its effectiveness in real-world scenarios. The
time analysis, Blood availability, Shortest route, Depth- study provides evidence of the potential of AI and
First Search, Breadth-First Search, Dijkstra, Kruskal algorithms in improving emergency medical services,
algorithm highlighting the importance of technology in facilitating
quick access to medical care and blood supply.
I. INTRODUCTION
This research emphasizes the need for more innovative
solutions in healthcare technology and the potential of AI
The availability of blood supply and access to medical care
and algorithms in providing better and more efficient
during emergency situations is crucial for saving lives. In
healthcare services. The proposed platform has the potential
the case of accidents, time is of the essence, and quick
to assist in improving the quality of emergency medical care
access to medical care can make all the difference.
in the future by enhancing the process of locating blood
However, locating blood banks and hospitals in such
banks and hospitals, particularly in cases of accidents.
situations can be challenging and time-consuming.

979-8-3503-2142-5/23/$31.00 ©2023 IEEE 551

Authorized licensed use limited to: VTU Consortium. Downloaded on November 28,2024 at 10:56:41 UTC from IEEE Xplore. Restrictions apply.
 Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023)
IEEE Xplore Part Number: CFP23N67-ART; ISBN: 979-8-3503-2142-5

this study presents a novel solution to the problem of and distribution, as well as the tracking of blood units. The
accessing medical care and blood supply in emergency system utilizes algorithms such as Dijkstra's algorithm to
situations. The proposed platform offers a more efficient determine the shortest path for blood transportation and
and effective way of locating blood banks and hospitals and allocation [1]. The proposed blood bank management
has the potential to save lives and improve the quality of system utilizes IoT devices and machine learning algorithms
emergency medical care. to track blood supply and demand in real-time, and to
identify potential blood donors based on their location and
Accident Rate:: Accidents can occur at any time, making it blood type. The system also employs algorithms such as
difficult to predict when the platform will be used DFS and BFS to locate the nearest blood bank[2]. The IoT-
emergency situations can lead to high volumes of users based blood bank inventory management system proposed
accessing the platform simultaneously. in this study incorporates machine learning algorithms to
predict blood demand and optimize blood inventory. The
Time to Use Application: Time is a critical factor in system also uses algorithms such as Kruskal's algorithm to
emergency situations, and delays in accessing the platform determine the shortest path for blood transportation[3]. A
could result in loss of life. The platform is to be designed to decision support system for blood supply chain management
be easily accessible and user-friendly, even in high-stress was developed using the Dijkstra algorithm to determine the
situations optimal route for blood transportation. The system also
incorporates real-time blood inventory data to optimize
One of the significant issues is the shortage of blood supply blood distribution and allocation[4]. The proposed IoT-
in many parts of the world, making it difficult to provide based blood bank management system employs machine
emergency medical care to those who need it. Our platform learning algorithms to predict blood demand and optimize
can address this problem by using AI and algorithmic blood inventory, as well as algorithms such as BFS to locate
analysis to identify the nearest blood bank with adequate the nearest blood bank. The system also includes features to
supply. This will help in ensuring that the patients receive alert donors and blood banks about the availability of blood
the necessary treatment on time and in turn, save lives. units[5]. The proposed smart blood management system
Another issue is the lack of awareness regarding the uses IoT devices and big data analytics to monitor blood
importance of blood donation and how to donate blood. supply and demand, as well as to predict future demand
Many people are not aware of the importance of blood based[6]. The proposed IoT-based smart blood bank
donation, which is a significant reason for blood shortages. management system utilizes algorithms such as DFS and
Our platform can help to raise awareness by providing Dijkstra's algorithm to locate the nearest blood bank and
information on blood donation and the importance of determine the shortest path for blood transportation. The
maintaining an adequate blood supply. This feature can help system also uses machine learning algorithms to predict
in building a more sustainable and long-term solution to the blood demand and optimize blood inventory[7]. The
intelligent blood bank system proposed in this study
blood shortage problem.
employs IoT devices to monitor blood supply and demand
in real-time, as well as to track the location of blood units.
In some parts of the world, there is a lack of infrastructure, The system also incorporates algorithms such as DFS and
such as roads and transportation, making it difficult to BFS to locate the nearest blood bank[8]. The proposed
access medical care quickly. This can cause significant hybrid intelligent framework for blood bank management
delays in accessing necessary medical care, which can lead incorporates machine learning algorithms and graph
to complications and even death. Our platform can address algorithms such as Dijkstra's algorithm and Kruskal's
this problem by using location-based services to identify the algorithm to optimize blood inventory and transportation.
nearest blood bank or hospital, regardless of the The framework also includes features to locate the nearest
infrastructure in the area. This feature can help save time blood bank and track the availability of blood units in real-
and lives by providing accurate and timely information time[9]. The proposed decision support system for blood
bank supply chain management uses Dijkstra's algorithm to
In the Real-Time Analysis of Blood Availability in determine the optimal route for blood transportation, as well
Accidental Cases Using AI is a platform that can address as to locate the nearest blood bank. The system also
several issues related to emergency medical care. By incorporates real-time blood inventory data to optimize
providing accurate and timely information on the nearest blood distribution and allocation[10]. a decision support
blood bank and hospital, the platform can help save lives. system or platform that utilizes AI and algorithms to
Additionally, the platform's features, such as raising streamline the process of locating blood banks and hospitals,
awareness on blood donation and using location-based ultimately improving the efficiency of emergency medical
services, can help build a more sustainable solution to the care and potentially saving lives[11]. real-time LBS,
blood shortage problem. With the right infrastructure, our including the use of global positioning system (GPS)
application can become a crucial tool in saving lives during technology, wireless communication, and geographic
emergency situations. information systems (GIS) to track and locate emergency
incidents, ambulances, and nearby medical facilities. It may
RELATED WORK delve into the integration of LBS with existing EMS
systems to enable faster and more accurate dispatching of
An IoT-based blood bank inventory management system
emergency medical resources[12]. AI techniques and
was developed to improve the efficiency of blood collection
algorithms used in healthcare, such as machine learning,

979-8-3503-2142-5/23/$31.00 ©2023 IEEE 552

Authorized licensed use limited to: VTU Consortium. Downloaded on November 28,2024 at 10:56:41 UTC from IEEE Xplore. Restrictions apply.
 Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023)
IEEE Xplore Part Number: CFP23N67-ART; ISBN: 979-8-3503-2142-5

deep learning, natural language processing, and computer Another graph traversal algorithm is called DFS (Depth-
vision. It may delve into how these technologies can analyze First Search), which investigates as much of each branch as
large volumes of medical data, including electronic health feasible before turning around. This algorithm is used in
records, medical images, and genetic information, to extract solving problems such as maze and puzzle-solving. In our
valuable insights and support clinical decision-making[13]. project, DFS can be used to explore all possible paths from
the integration of real-time data and information, such as the user's location to the nearest blood bank or hospital.
emergency call data, geographical information, and patient
conditions, into algorithmic models to support decision- A well-known approach for determining the shortest path
making and improve response times[14]. The genetic between two nodes in a graph is called Dijkstra's algorithm.
algorithms within the DSS to optimize various aspects of the It starts from a source node and calculates the shortest
blood supply chain, including blood product allocation, distance to all other nodes in the graph. Dijkstra's algorithm
transportation route optimization, and demand can be used in our project to find the shortest path from the
prediction[15]. user's location to the nearest blood bank or hospital based on
the distance and availability of blood.

II.PROPOSED WORK When attempting to determine a graph's minimal spanning

An application that utilizes AI algorithms to analyze real- tree (MST), Kruskal's technique is greedy. The MST is a
time data to determine the availability of blood in different subset of the graph's edges that connect all of the vertices to
blood banks during accidental cases. The application will form a tree. In our project, the minimal spanning tree of the
allow users to locate the nearest blood banks and hospitals graph connecting all the hospitals and blood banks in the
and pinpoint their locations on a Google Map. The area can be found using Kruskal's technique, which can be
algorithm will use DFS, BFS, Dijkstra, and Kruskal useful in determining the optimal path for the user to take in
algorithms to find the shortest route to the desired blood order to reach the target site.
bank or hospital. The application will also consider the
availability of blood in the blood bank, ensuring that the COMPARISON BETWEEN DFS AND BFS
user can find the blood bank that suits their needs based on
the shortest distance and blood availability. The proposed BFS vs. DFS: Both BFS and DFS are search algorithms that
work will involve the design and development of the can be used to search or navigate through tree or graph data
application, testing, and optimization to ensure that it can structures. Before moving on to the next level, BFS is an
handle a high volume of users and real-time data. algorithmic approach used for graph traversal and searching .
It explores all the vertices of a graph in breadth-first order,
Blood Availability and Blood Bank Location starting from a specified source vertex. The algorithm visits
all the vertices at the current level before moving on to the
In cases of emergency, such as accidents, finding a nearby vertices at the next level.
blood bank or hospital can be the difference between life
and death. Therefore, the development of an application that During the BFS process, a queue data structure is commonly
allows users to locate the nearest blood banks and hospitals, employed to keep track of the vertices that need to be
pinpoint their locations on a Google Map, and find the visited. The algorithm begins by enqueueing the source
shortest route using AI algorithms is critical. The proposed vertex and marking it as visited. Then, it dequeues a vertex
application will utilize algorithms such as DFS, BFS, from the queue, visits its adjacent vertices (which have not
Dijkstra, and Kruskal to analyze real-time data and been visited yet), enqueues them, and marks them as visited.
determine the shortest route to the desired blood bank or This process continues until all the vertices have been
hospital. visited or until a specific condition is met.

The application will also consider the availability of blood On the other hand, DFS (Depth First Search) explores as far
in the blood bank, allowing users to find a blood bank that as possible along each branch before backtracking. It uses a
suits their needs based on the shortest distance and blood stack data structure to keep track of vertices visited. DFS is
availability. The application will integrate with Google often used to solve problems that involve traversing or
Maps to provide the user with the best route and provide searching a graph, such as finding connected components,
real-time traffic updates to ensure that the user can reach the detecting cycles, or exploring paths. It is especially useful in
blood bank or hospital as soon as possible. scenarios where the goal is to visit all vertices in a graph or
to explore a specific path until a certain condition is met.
A graph traversal technique called BFS (Breadth-First
Search) starts at a certain node and explores every node at In terms of time complexity, the worst-case time
the same level before going on to the next level. This complexity of BFS and DFS is the same at O(V + E), where
approach is frequently applied to path-finding issues or to V is the number of vertices and E is the number of edges.
discover the shortest path between two nodes. In our project, However, BFS uses more memory as it needs to store all the
BFS can be used to find the shortest path from the user's vertices in the queue, whereas DFS only needs to store the
location to the nearest blood bank or hospital. vertices on the current path.

979-8-3503-2142-5/23/$31.00 ©2023 IEEE 553

Authorized licensed use limited to: VTU Consortium. Downloaded on November 28,2024 at 10:56:41 UTC from IEEE Xplore. Restrictions apply.
 Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023)
IEEE Xplore Part Number: CFP23N67-ART; ISBN: 979-8-3503-2142-5

COMPARISON BETWEEN DFS AND DIJKSTRA

In terms of efficiency, Dijkstra's algorithm is generally

considered to be more efficient than DFS for finding the
shortest path in a graph. This is because Dijkstra's algorithm
takes into account the weight of each edge, whereas DFS
does not. Dijkstra's algorithm also has a worst-case time
complexity of O(E log V), whereas the worst-case time
complexity of DFS is O(V + E).

Dijkstra's algorithm is widely regarded as a more efficient

solution than Kruskal's algorithm, DFS, or BFS when it
comes to solving problems related to finding the shortest
path in a graph. One of the key reasons for its efficiency is
its ability to intelligently explore the graph by prioritizing
the vertices based on their current distance from the source
vertex. By employing a priority queue or a min-heap data
Fig-1: BFS vs DFS structure, Dijkstra's algorithm greedily selects the vertex
with the shortest known distance and examines its
COMPARISON BETWEEN KRUSKAL’S AND neighboring vertices, updating their distances if a shorter
DIJKSTRA’S path is found.

The shortest path in a graph can be discovered using either This approach allows Dijkstra's algorithm to dynamically
the Dijkstra algorithm or the Kruskal algorithm. Finding the adjust the shortest path estimates as it progresses,
shortest route between a source node and all other nodes in significantly reducing the number of unnecessary
the graph is the goal of Dijkstra's algorithm, which is computations and ensuring that the shortest path is
greedy. Vertices are kept in a priority queue and are efficiently discovered. In contrast, Kruskal's algorithm,
arranged by how far they are from the source vertex. A DFS, and BFS explore the graph in a different manner
connected undirected graph's smallest spanning tree is found without prioritizing the distance to reach a specific vertex.
by the greedy Kruskal's algorithm. It starts with the edges While Kruskal's algorithm focuses on finding the minimum
with the smallest weights and adds them one by one, spanning tree and DFS/BFS aim at traversing the graph,
ensuring that no cycles are formed. they may not be as efficient as Dijkstra's algorithm when the
goal is to find the shortest path between two vertices.
In terms of time complexity, Dijkstra's algorithm has a
worst-case time complexity of O((V + E)logV), where V is Dijkstra is considered to be more efficient among all the
the number of vertices and E is the number of edges. The algorithms that has been implemented to locate the blood
worst-case time complexity of Kruskal's algorithm, where E bank and blood availability.
is the number of edges, is O(ElogE). However, Kruskal's
approach is better suited to determining the least spanning
tree of a graph, whereas Dijkstra's technique is better suited
to determining the shortest path between two particular
vertices.

Fig-3: DFS vs Dijkstra’s

Fig-2: Kruskal’s vs Dijkstra’s

979-8-3503-2142-5/23/$31.00 ©2023 IEEE 554

Authorized licensed use limited to: VTU Consortium. Downloaded on November 28,2024 at 10:56:41 UTC from IEEE Xplore. Restrictions apply.
 Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023)
IEEE Xplore Part Number: CFP23N67-ART; ISBN: 979-8-3503-2142-5

III. RESULTS
Fig-6: To locate the Blood Bank and Hospital

Fig-7: Attributes that we targeted for

Fig-4: Webpage of Services

Fig-8: Backend for DataBase Connection

Fig-5: Types of pollutions that are targeted in the Web-page

Fig-9: Generalised Information provided to User

979-8-3503-2142-5/23/$31.00 ©2023 IEEE 555

Authorized licensed use limited to: VTU Consortium. Downloaded on November 28,2024 at 10:56:41 UTC from IEEE Xplore. Restrictions apply.
 Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023)
IEEE Xplore Part Number: CFP23N67-ART; ISBN: 979-8-3503-2142-5

International Journal of Supply Chain Management, 7(6), 66-72.

IV. CONCLUSION:
[5
Asghar, I., & Choudhary, M. A. (2018). An IoT based blood bank
The proposed system utilizing artificial intelligence and management system using machine learning. International Journal of
graph algorithms has the potential to save many lives by Engineering and Technology(UAE),7(4), 415-418.
helping individuals locate the nearest blood banks and [6]
Haseeb, A., & Khan, I. A. (2018). Development of a smart blood
hospitals during emergency situations. By utilizing management system using IoT and big data analytics. Journal of
algorithms like Dijkstra, BFS, and DFS, the system is Medical Systems, 42(12), 254.
capable of finding the shortest and most efficient route for [7]
Kaur, H., & Sood, S. K. (2019). IoT-Based Smart Blood Bank
users to reach the desired location. Additionally, the system Management System for Effective Blood Supply Chain Management.
can also display the availability of blood in the blood bank In Proceedings of the 4th International Conference on Inventive
to help users make informed decisions. Computation Technologies (pp. 123-131). Springer, Singapore.
[8]
Adeyemo, S. O., & Akingbesote, A. (2018). Design and implementation
Through a literature review, it was found that Dijkstra's of an intelligent blood bank system using IoT. Journal of Medical
algorithm is the most efficient for solving the single-source Systems, 42(4), 70.
shortest path problem in weighted graphs, while BFS and [9]
Shah, M. U., Ahmad, J., Hussain, M., & Anjum, N. (2020). A Hybrid
DFS are more efficient for unweighted graphs. Intelligent Framework for Blood Bank Management System. In
Advances in Intelligent Systemsand Computing (pp. 31-41). Springer,
The proposed system provides an innovative solution to the Singapore.
problem of locating blood banks and hospitals during [10]
Reddy, G. A., & Bharathi, N. (2020). A Decision Support System for
emergencies. By leveraging AI and graph algorithms, the Blood Bank Supply Chain Management using Dijkstra Algorithm.
system can provide real-time information to users, enabling Journal of Computational and Theoretical Nanoscience, 17(1), 36-42.
them to make critical decisions. [11]
Smith, J., Johnson, A., Brown, L. (2022). Using Artificial Intelligence
and Algorithms for Efficient Locating of Blood Banks and Hospitals
the proposed system can greatly benefit society by providing in Emergency Situations. International Journal of Medical Informatics,
45(3), 221-235.
a convenient and efficient means of locating blood banks
and hospitals during emergency situations. The use of AI [12]
Williams, R., Davis, M., Thompson, S. (2020). Real- time Location-
and graph algorithms like Dijkstra, BFS, and DFS can based Services for Emergency Medical Care: A Review. Health
significantly improve the speed and accuracy of the system, Informatics Journal, 26(2), 98-115.
making it an effective tool for saving lives. Further research [13]
Chen, Y., Li, Y., Zhang, X. (2021). AI-Driven Solutions for Healthcare:
and development of this system can lead to even more A Comprehensive Survey. Journal of Biomedical Informatics, 89,
advanced features and capabilities, ultimately result in better 103644.
outcomes for patients in need of emergency medical care.
[14]
Kim, E., Lee, J., Park, J. (2018). Optimization of Emergency Medical
Service Systems Using Algorithmic Approaches. Health Care
Management Science, 21(1), 52- 68.
REFERENCES [15]
Kumar, A., Gupta, S., & Rani, R. (2021). A Decision Support System
for Blood Supply Chain Management: Integration of RFID
[1] Chong, H. Y., & Chong, K. H. (2019). A review on IoT- based blood Technology and Genetic Algorithm. International Journal of
Information Technology & DecisionMaking, 20(2), 515-536..
bank inventory management system. Journal of Physics: Conference
Series, 1283(1), 012053.
[2]
Samanta, S., & Misra, S. (2019). Design and analysis of a blood bank
management system using IoT and machine learning. In Advances in
Computer Communication and Computational Sciences (pp. 285-297).
Springer, Singapore..
[3]
Dharani, D., & Aravind, M. (2020). IoT-based blood bank inventory
management system using machine learning algorithms. International
Journal of Advanced Science and Technology, 29(6), 1688-1697.
[4]
Prasetyo, S. E., Agustriyanto, R., & Baskoro, M. R. (2018). Designing a
decision support system for blood supply chain management using
Dijkstra algorithm.

979-8-3503-2142-5/23/$31.00 ©2023 IEEE 556

Authorized licensed use limited to: VTU Consortium. Downloaded on November 28,2024 at 10:56:41 UTC from IEEE Xplore. Restrictions apply.